Generative AI for Industrial Contour Detection: A Language-Guided Vision System

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Gong, Liang, Tommy, Wang, Chaker, Sara, Dong, Yanchen, Bousetouane, Fouad, Morton, Brenden, Mendez, Mark
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914014428135424
author Gong, Liang
Tommy
Wang
Chaker, Sara
Dong, Yanchen
Bousetouane, Fouad
Morton, Brenden
Mendez, Mark
author_facet Gong, Liang
Tommy
Wang
Chaker, Sara
Dong, Yanchen
Bousetouane, Fouad
Morton, Brenden
Mendez, Mark
contents Industrial computer vision systems often struggle with noise, material variability, and uncontrolled imaging conditions, limiting the effectiveness of classical edge detectors and handcrafted pipelines. In this work, we present a language-guided generative vision system for remnant contour detection in manufacturing, designed to achieve CAD-level precision. The system is organized into three stages: data acquisition and preprocessing, contour generation using a conditional GAN, and multimodal contour refinement through vision-language modeling, where standardized prompts are crafted in a human-in-the-loop process and applied through image-text guided synthesis. On proprietary FabTrack datasets, the proposed system improved contour fidelity, enhancing edge continuity and geometric alignment while reducing manual tracing. For the refinement stage, we benchmarked several vision-language models, including Google's Gemini 2.0 Flash, OpenAI's GPT-image-1 integrated within a VLM-guided workflow, and open-source baselines. Under standardized conditions, GPT-image-1 consistently outperformed Gemini 2.0 Flash in both structural accuracy and perceptual quality. These findings demonstrate the promise of VLM-guided generative workflows for advancing industrial computer vision beyond the limitations of classical pipelines.
format Preprint
id arxiv_https___arxiv_org_abs_2509_00284
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generative AI for Industrial Contour Detection: A Language-Guided Vision System
Gong, Liang
Tommy
Wang
Chaker, Sara
Dong, Yanchen
Bousetouane, Fouad
Morton, Brenden
Mendez, Mark
Computer Vision and Pattern Recognition
Artificial Intelligence
Industrial computer vision systems often struggle with noise, material variability, and uncontrolled imaging conditions, limiting the effectiveness of classical edge detectors and handcrafted pipelines. In this work, we present a language-guided generative vision system for remnant contour detection in manufacturing, designed to achieve CAD-level precision. The system is organized into three stages: data acquisition and preprocessing, contour generation using a conditional GAN, and multimodal contour refinement through vision-language modeling, where standardized prompts are crafted in a human-in-the-loop process and applied through image-text guided synthesis. On proprietary FabTrack datasets, the proposed system improved contour fidelity, enhancing edge continuity and geometric alignment while reducing manual tracing. For the refinement stage, we benchmarked several vision-language models, including Google's Gemini 2.0 Flash, OpenAI's GPT-image-1 integrated within a VLM-guided workflow, and open-source baselines. Under standardized conditions, GPT-image-1 consistently outperformed Gemini 2.0 Flash in both structural accuracy and perceptual quality. These findings demonstrate the promise of VLM-guided generative workflows for advancing industrial computer vision beyond the limitations of classical pipelines.
title Generative AI for Industrial Contour Detection: A Language-Guided Vision System
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2509.00284